Reporium
GraphWikiTaxonomyStacksInsightsTrendsArchitectureAI-NativeFAQ
Ask anything about the repo library…
Loading repo…
←Library/bitsandbytes
Library/bitsandbytesForked

bitsandbytes-foundation/bitsandbytes

bitsandbytes

Accessible large language models via k-bit quantization for PyTorch.

View on GitHub↗Upstream bitsandbytes-foundation/bitsandbytes↗

Builder

bitsandbytes-foundation

bitsandbytes-foundation

bitsandbytes-foundation • individual

Stars

8,237

Using upstream star count

Forks

856

Using upstream fork count

Open Issues

0

Activity Score

0/100

0 commits in 30d

Created

Jun 4, 2021

Project creation date

README Summary

<p align="center"><img src="https://avatars.githubusercontent.com/u/175231607?s=200&v=4" alt=""></p> <h1 align="center">bitsandbytes</h1> <p align="center"> <a href="https://github.com/bitsandbytes-foundation/bitsandbytes/main/LICENSE"><img alt="License" src="https://img.shields.io/github/license/bitsandbytes-foundation/bitsandbytes.svg?color=blue"></a> <a href="https://pepy.tech/project/bitsandbytes"><img alt="Downloads" src="https://static.pepy.tech/badge/bitsandbytes/month"></a> <

Community Evaluation

Loading…

AI Dev Skills

Unmapped

CUDA ProgrammingGPU Memory ManagementLarge Language Model DeploymentMemory OptimizationMixed Precision TrainingNeural Network QuantizationPyTorch IntegrationWeight Compression

Tags

CUDA ProgrammingGPU Memory ManagementLarge Language Model DeploymentMemory OptimizationMixed Precision TrainingNeural Network QuantizationPyTorch IntegrationWeight CompressionFine-TuningForkedGPU / CUDAHuggingFaceLarge Language ModelsLoRA / PEFTPyTorchPythonQuantizationResearch / PapersTransformers

Taxonomy

AI Trends

On-device AISmall Language ModelsEfficient AIDemocratized AI Access

category

Foundation ModelsModel TrainingInference & ServingLearning Resources

Deployment Context

Self-hostedEdge/MobileOn-premise

Modalities

Text

Skill Areas

Neural Network QuantizationMemory OptimizationLarge Language Model DeploymentCUDA ProgrammingPyTorch IntegrationWeight CompressionMixed Precision TrainingGPU Memory Management

tag

Fine-TuningForkedGPU / CUDAHuggingFaceLarge Language ModelsLoRA / PEFTPyTorchPythonQuantizationResearch / PapersTransformers

Use Cases

Large Language Model Deployment on Consumer GPUsMemory-Constrained Model TrainingModel Compression for Edge DeploymentFine-tuning Large Models on Limited HardwareInference Optimization

Recent Activity

Updated 2 months ago

7 Days

0

30 Days

0

90 Days

8

Enable Paged Optimizer Support for XPU (#1898)

jiqing-feng • Mar 17, 2026

ecf9ca1

Merge pull request #1893 from ailuntz/fix/matmul-4bit-out

BADAOUI Abdennacer • Mar 13, 2026

925d83e

Honor out in matmul_4bit

ailuntz • Mar 10, 2026

c25c294

Quality

production
Quality
high
Maturity
production

Categories

Inference & ServingPrimaryLearning ResourcesFoundation ModelsModel TrainingSearch & Knowledge

PM Skills

Cost & Efficiency

Languages

Python100.0%

Timeline

Project created
Jun 4, 2021
Forked
Mar 22, 2026
Your last push
2 months ago
Upstream last push
19 days ago
Tracked since
Mar 17, 2026

Similar Repos

pgvector cosine similarity · $0

Loading…